Harrison Clarke ยท 1 day ago
Senior Research Engineer
Harrison Clarke is a fast-growing, deeply technical AI company looking for a Senior Research Engineer to join their team. The role involves designing and evaluating models for understanding and generating complex codebases, while collaborating with product and engineering teams to enhance model performance.
Responsibilities
Design and run large-scale LLM evaluations, benchmarks, and experiments - particularly for code understanding and generation tasks
Build tools, datasets, and research frameworks that measure LLM reasoning, reliability, grounding, and hallucination reduction
Collaborate closely with product and engineering teams to improve model performance across real-world developer workflows
Work with frontier LLMs (across multiple providers) to analyze behavior, provide structured feedback, and drive improvements in accuracy, reliability, and autonomy
Prototype new capabilities for long-horizon agentic systems, including retrieval, planning, debugging, and automated coding workflows
Contribute to model fine-tuning and alignment work, including SFT, LoRA, DPO, or RLHF pipelines
Build production-quality research tools and evaluation pipelines that scale to real engineering environments
Qualification
Required
3+ years of experience in AI/ML engineering, research engineering, or similar fields
Strong coding fundamentals and comfort working in production environments (Python preferred)
Hands-on experience with LLMs (training, fine-tuning, benchmarking, or evaluation)
Experience with transformer architectures, retrieval-augmented generation (RAG), or reasoning-heavy LLM workflows
Deep interest in code generation, AI developer tools, or program synthesis (professional or personal projects)
Ability to think rigorously about model behavior, failure cases, and reliability
Comfortable working in a fast-paced, highly collaborative environment with end-to-end ownership
Preferred
Experience with AI systems for code: program synthesis, automated debugging, static analysis, code search, etc
Prior work with agentic or multi-step reasoning systems
Contributions to evaluation frameworks, benchmarks, or open-source model tooling
Background in compilers, programming languages, distributed systems, or developer tooling
Research experience at top universities, labs, or advanced ML teams