Research Engineer — Post-Training & Small Language Models (SLMs), Healthcare AI

Three hundred fifty million Americans rely on a healthcare system whose decision-making has become slow, costly, and adversarial—care delayed by prior authorization and paperwork, claims that misfire, clinical decisions made without the right information at the right moment, and patients who struggle to navigate or afford the care they need. Deloitte’s new AI-first effort, backed by $1B in committed investment, is building the reasoning models and agentic systems to rebuild how that system decides—across payers, providers, and life sciences, and for the patients they serve—so that care is faster, fairer, and far less wasteful. This is a ground-up rebuild of the decision-making machinery behind American healthcare, at national scale, with real post-training at scale—committed investment in GPU compute and training infrastructure, not toy fine-tunes.

About the role

As a Research Engineer on our post-training team, you will design, train, evaluate, and align the models that reason about healthcare—working across the full post-training lifecycle to shape model behavior for clinical and operational decisioning. Healthcare decisioning is one of the cleanest verifiable-reward domains outside math and code: the problems are hard, and correctness is checkable rather than asserted, grounded in real signals like clinical policy, adjudicated outcomes, and clinical-expert judgment. You will own the post-training stack for our clinical reasoning models end-to-end—from data and reward design through trained, evaluated models that ship. This is not a prompt-engineering role; we seek people who understand how to improve and shape model behavior through advanced post-training. No healthcare background is required—we pair every engineer with clinical and domain experts to teach you the domain.

Responsibilities

• Design and execute post-training pipelines: supervised fine-tuning (SFT), preference optimization, and reinforcement learning/alignment workflows.
• Build and optimize training using techniques such as SFT, RLHF, PPO, DPO, GRPO, RLAIF, and Constitutional AI, understanding how each affects reasoning quality, safety, latency, cost, and reliability.
• Train reasoning models for healthcare decisioning using verifiable-reward RL—designing reward signals and verifiers grounded in clinical guidelines, policy, and adjudicated outcomes.
• Develop reward models and preference datasets to improve reasoning quality, factuality, safety, policy adherence, and task performance.
• Curate, clean, synthesize, and evaluate large-scale instruction, preference, and domain-specific datasets with rigorous filtering, deduplication, and quality control.
• Build verification and reward pipelines from proprietary clinical, claims, and operational data and clinical-expert labeling—turning guidelines, policy, and adjudicated outcomes into checkable reward signals at scale.
• Implement efficient fine-tuning strategies including LoRA, QLoRA, PEFT, and adapter-based approaches; build scalable distributed training using DeepSpeed, FSDP, Megatron-LM, Ray, or equivalent.
• Optimize inference performance—latency, throughput, quantization, and deployment efficiency—for production, including frameworks such as vLLM, TensorRT-LLM, or TGI.
• Train and optimize open-weight models (e.g., Llama, Qwen, Mistral, DeepSeek) and build specialized small language models (SLMs) for on-premise and cloud-hybrid deployment with strong performance-per-dollar.
• Design evaluation frameworks covering reasoning, hallucination detection, factuality, instruction following, structured outputs, and domain-specific metrics.
• Build healthcare-grade evaluation—held-out clinical benchmarks, deployment regression gates, calibration and uncertainty, factuality against ground truth, and bias/fairness evaluation across patient populations—co-designed with clinical experts.
• Apply PHI/HIPAA-aware data handling and produce model documentation suitable for regulated clinical use.
• Perform red teaming and adversarial testing to identify alignment failures, unsafe behaviors, jailbreak vulnerabilities, and regression risks; collaborate with agentic and application teams to improve tool use, grounding, and long-horizon reasoning.

The team

Deloitte brings together AI researchers, modeling and platform engineers, architects, clinical and domain specialists, and product leaders to build, deploy, and operate verticalized AI systems across software, data, models, and cloud infrastructure—engineered for one of the most complex operating environments in the world. The work spans the healthcare industry—payers, providers, and life sciences—and involves genuinely hard reasoning problems, nuanced operational workflows, and a high bar for reliability, with little tolerance for shallow or unreliable outputs. We pair frontier AI research with production-grade engineering, shipping into real clinical and operational settings rather than leaving models in the lab. The team sub-specializes across post-training research, data and reward engineering, and training and inference infrastructure—you won’t be expected to own all of it alone.

Requirements

• Bachelor’s degree in Computer Science, Machine Learning, Artificial Intelligence, Applied Mathematics, Computational Linguistics, or a related field.
• Demonstrated depth training and post-training large transformer-based language models in production or research—this is your craft, not coursework or a one-off fine-tune.
• Genuine depth including SFT and at least one preference-optimization or RL method, evidenced by shipped models, releases, or research.
• Hands-on experience with reasoning-model training and/or verifiable-reward (RLVR) workflows.
• Strong understanding of modern post-training techniques: SFT, RLHF, PPO, DPO, GRPO, RLAIF, and preference optimization workflows.
• Experience with open-weight foundation models such as Llama, Qwen, Mistral, DeepSeek, or equivalent architectures.
• Strong expertise in PyTorch and modern deep-learning tooling; experience with distributed training frameworks such as DeepSpeed, FSDP, Megatron-LM, or Ray.
• Experience implementing efficient fine-tuning techniques such as LoRA, QLoRA, PEFT, and quantization-aware workflows.
• Deep understanding of transformer architectures, tokenization, attention mechanisms, decoding strategies, and model scaling trade-offs.
• Strong grasp of LLM evaluation methodologies, benchmarking, reward modeling, and alignment trade-offs; experience with large-scale and synthetic datasets, filtering, deduplication, and quality-control pipelines.
• Strong Python engineering skills and production-grade software practices; ability to work through ambiguous, highly complex technical problems in fast-moving environments.
• Ability to travel 0-50%, on average, based on the work you do and the clients and industries/sectors you serve.
• Limited immigration sponsorship may be available.

Preferred Qualifications

• Experience building or optimizing reasoning models, agentic models, or tool-using LLM systems.
• Familiarity with inference optimization frameworks such as vLLM, TensorRT-LLM, TGI, or Ollama.
• Experience with multimodal models, speech models, or domain-specific foundation models; experience using large-scale GPU clusters and distributed compute.
• Contributions to open-source AI projects, research publications, benchmark development, or model releases.
• Familiarity with safety, governance, and responsible-AI practices; experience in regulated or high-stakes industries such as healthcare, finance, insurance, or public sector.

Pay

The wage range for this role takes into account factors such as skill sets, experience, training, licensure, certifications, and business needs. The disclosed range estimate has not been adjusted for geographic differentials. A reasonable estimate of the current range is $110,700–$379,200. At Deloitte, it is not typical for an individual to be hired at or near the top of the range, and compensation decisions depend on the facts and circumstances of each case.

Benefits

This position is aligned with the Core Talent Model. To view the associated benefit package, please reference this document.