Senior Solution Architect

We need to output HTML fragment with sections: headings

for sections like About the role, Responsibilities, Requirements, Qualifications, Skills, Benefits, Pay, Schedule. We must only include sections that have real specific content. The posting includes responsibilities, requirements, benefits, pay (salary range). Also maybe "Qualifications" is similar to requirements; we can combine. The instructions: use

for section headings (e.g. About the role, Responsibilities, Requirements, Qualifications, Skills, Benefits, Pay, Schedule). Use

• for any list of duties/requirements/benefits, and

  for prose. Do NOT repeat the job title as a heading. Do NOT put Job ID / requisition numbers as headings — fold minor metadata into a short

  or drop it. Preserve ALL substantive information; do NOT invent or summarize away detail. Remove cookie/navigation/legal/EEO/equal-opportunity/scam-warning boilerplate, duplicated lines, and application instructions. IMPORTANT: include a section ONLY when the posting has real, specific content for it — never emit a heading followed by filler/placeholder text (e.g. "commensurate with experience", "not specified", "N/A", "varies", "TBD") and never create Pay/Schedule/Benefits sections unless the posting actually states them. Prefer a few substantive sections over many thin ones. Thus we need sections: About the role (maybe a short paragraph summarizing role), Responsibilities (list), Requirements (list), Benefits (list), Pay (salary range). Possibly also Qualifications but we can merge with Requirements. The posting includes "Requirements" and "Nice to have". We could separate Requirements (must have) and Nice to have as separate list under Requirements? But we can keep one Requirements section with sublists? The instruction: use

  • for any list of duties/requirements/benefits. So we can have separate sections for Responsibilities, Requirements, Benefits, Pay. Possibly also "About the role" as prose. We need to preserve all substantive information: responsibilities list, requirements list (including nice-to-have?), benefits list, pay range. We must remove boilerplate: legal, EEO, etc. Also remove application instructions, H-1B note, Massachusetts lie detector test, etc. Also remove "Req# 1090267686" maybe fold into short p or drop. Probably drop. We need to output only HTML fragment, no /, no markdown fences. Let's extract responsibilities bullet points: From posting: "Design end-to-end architectures for AI-native solutions: orchestration, retrieval, tool and system integration, agent autonomy and guardrails, identity and authorization, evaluation, observability, and cost model" "Fit each solution exactly to the business scope - no more, no less - and be able to explain what you deliberately left out and why" "Turn incoherent or contradictory requirements into explicit business decisions: surface them, reframe them in business terms, price the options, and get a named owner to decide" "Make and document architectural trade-offs (build vs buy, model selection, retrieval strategy, autonomy level, cost vs quality) in a form that stakeholders can challenge and future teams can trust" "Define the evaluation strategy for each system: how we will know that an assistant or agent fits the business scope, not just that it produces fluent output" "Author the constraints, guidelines, and architectural fitness functions that engineering teams and coding agents build within, and revise them as the organization learns what generation gets wrong" "Decide where humans must stay in the loop - regulated decisions, data of record, security boundaries, anything with legal or contractual consequence" "Work within EPAM delivery teams and in presales: shape proposals, present options and costs to client executives, and review designs across teams" "Build proofs of concept and reference implementations when, and only when, a decision needs evidence or a team needs an example of 'good'" "Contribute to EPAM's AI architecture practice: reference architectures, reusable patterns, and mentoring architects who are transitioning into AI-native design" That's responsibilities. Now Requirements (must have): "You have architected AI-native systems in production - RAG, assistants, agents or agentic workflows with real users or real business processes behind them - and you held architect-level responsibility for the system around the model" "You are a proven solution or software architect with a strong production track record who has started building with AI on your own initiative in the last year or so - a side project, a proof of concept, an internal tool, published writing - and wants to make AI-native design the center of your work" "Solid experience as a solution, software, or enterprise architect with delivery accountability: systems you designed that shipped, ran, and were maintained over time" "Depth in distributed systems, integration, cloud, and data-flow architecture at enterprise scale" "Demonstrated ability to work with ambiguous, conflicting requirements and to make trade-offs explicit rather than resolving them silently" "Experience presenting options, costs, and risks to non-technical decision makers and getting decisions made" "A habit of writing things down: architecture decision records, design documents, reference architectures that other teams built from" "Recent hands-on coding ability, enough to prototype and to keep your constraints honest" "Understanding of how AI-assisted development changes the architect's role: what to specify, what to evaluate, and where to keep human judgment" Nice to have (optional): "Experience in regulated industries - financial services, healthcare and life sciences, insurance" "Agent frameworks, tool and function calling, MCP, orchestration patterns, LLM observability" "Identity and authorization for agentic systems (OAuth 2.1, SPIFFE, AuthZEN, DPoP)" "Ownership of cost and token economics for a production AI system" "Consulting or pre-sales experience" "Published writing, talks, or open-source contributions on AI architecture" We could include nice-to-have as part of Requirements section maybe as a sublist labeled "Nice to have". But instruction: use
    • for any list of duties/requirements/benefits. So we can have a Requirements section with two sublists? Could just combine all items into one list, but we might lose distinction. Probably okay to combine; but we should preserve all info. We'll include both must-have and nice-to-have as separate
      maybe with a preceding

      indicating nice-to-have. That's still a list. Benefits list: "Medical, Dental and Vision Insurance (Subsidized)" "Health Savings Account" "Flexible Spending Accounts (Healthcare, Dependent Care, Commuter)" "Short-Term and Long-Term Disability (Company Provided)" "Life and AD&D Insurance (Company Provided)" "Employee Assistance Program" "Unlimited access to LinkedIn learning solutions" "Matched 401(k) Retirement Savings Plan" "Paid Time Off – the employee will be eligible to accrue 15-25 paid days, depending on specific level and tenure with EPAM (accrual eligibility may change over time)" "Paid Holidays - nine (9) total per year" "Legal Plan and Identity Theft Protection" "Accident Insurance" "Employee Discounts" "Pet Insurance" "Employee Stock Purchase Program" "If otherwise eligible, participation in the discretionary annual bonus program" "If otherwise eligible and hired into a qualifying level, participation in the discretionary Long-Term Incentive (LTI) Program" Also note: "For remote work in New York City only." That's a location constraint; maybe we can include as a short p under About the role or separate? It's substantive. Could be part of About the role. Pay: Salary range: $160,000 - $230,000. Schedule: Not mentioned; we should not create Schedule section. About the role: We can summarize from first paragraph: "Enterprises are past the point of asking whether AI belongs in their systems. The question now is which AI capabilities should exist, how much autonomy each one earns, how they integrate with systems of record and real business processes, and how anyone will know they are working. Answering those questions well - and writing the answers down so that engineering teams and coding agents can build against them - is the AI Architect's job. You will design the target architecture of AI-native applications, Enterprise AI and Applied AI solutions for large clients across industries, from assistants and RAG systems to agents, agentic workflows and autonomous components. You will decide what the system should do and, just as importantly, what it should not. You will define the evaluations, guardrails, and constraints that shape what gets built, whether the builder is an engineer or an AI coding agent. This is an architecture role. The output is decisions, structure, and the reasoning behind them - not code volume. You will still prototype when a decision needs evidence, but most of your time goes to framing problems, resolving conflicting requirements, making trade-offs explicit, and getting the right people to own them." We can put that as

      under About the role. Also include location note: "For remote work in New York City only." Could be a short p after About the role or within. We must not include boilerplate like "EPAM is a leading global provider..." etc. That's fluff but maybe considered boilerplate? It's descriptive but not required. The instruction: Remove cookie/navigation/legal/EEO/equal-opportunity/scam-warning boilerplate, duplicated lines, and application instructions. The paragraph about EPAM being leading global provider etc is not legal/EEO; it's marketing fluff. Might be considered boilerplate? Not sure. Safer to keep only substantive info about role, responsibilities, requirements, benefits, pay. The EPAM marketing paragraph may be considered filler; but it's not duplicated. However instruction: Prefer a few substantive sections over many thin ones. Could include a short About the role paragraph that captures the essence; we already have that from first part. The EPAM marketing paragraph may be redundant. We'll omit. Now construct HTML:

      About the role

      Enterprises are past the point of asking whether AI belongs in their systems. The question now is which AI capabilities should exist, how much autonomy each one earns, how they integrate with systems of record and real business processes, and how anyone will know they are working. Answering those questions well - and writing the answers down so that engineering teams and coding agents can build against them - is the AI Architect's job. You will design the target architecture of AI-native applications, Enterprise AI and Applied AI solutions for large clients across industries, from assistants and RAG systems to agents, agentic workflows and autonomous components. You will decide what the system should do and, just as importantly, what it should not. You will define the evaluations, guardrails, and constraints that shape what gets built, whether the builder is an engineer or an AI coding agent. This is an architecture role. The output is decisions, structure, and the reasoning behind them - not code volume. You will still prototype when a decision needs evidence, but most of your time goes to framing problems, resolving conflicting requirements, making trade-offs explicit, and getting the right people to own them.

      For remote work in New York City only.

      Responsibilities

      • Design end-to-end architectures for AI-native solutions: orchestration, retrieval, tool and system integration, agent autonomy and guardrails, identity and authorization, evaluation, observability, and cost model
      • Fit each solution exactly to the business scope - no more, no less - and be able to explain what you deliberately left out and why
      • Turn incoherent or contradictory requirements into explicit business decisions: surface them, reframe them in business terms, price the options, and get a named owner to decide
      • Make and document architectural trade-offs (build vs buy, model selection, retrieval strategy, autonomy level, cost vs quality) in a form that stakeholders can challenge and future teams can trust
      • Define the evaluation strategy for each system: how we will know that