1 day ago
Cambridge, MA, USAStaff+
Responsibilities
- Architect and implement agentic GenAI systems using modern LLM orchestration frameworks.
- Design multi-agent architectures, including planner-solver patterns, hierarchical agents, autonomous teams, and goal decomposition workflows.
- Define end-to-end GenAI architecture spanning model selection, orchestration, memory, tools, security, observability, and deployment.
- Build reusable agent tooling, APIs, and memory architectures for coordination, context persistence, and scalable interaction.
- Lead hands-on development and production deployment of assistants, copilots, workflow automation, and decision-support systems.
- Evaluate, integrate, and optimize LLMs, multimodal models, and RAG pipelines using vector databases and retrieval systems.
- Optimize GenAI systems for performance, reliability, scalability, cost efficiency, security, privacy, bias, and hallucination mitigation.
- Establish and enforce GenAIOps and LLMOps practices, including evaluation, monitoring, logging, feedback loops, and continuous improvement.
- Guide and mentor teams on agent design patterns, prompt engineering, tool abstraction, fine-tuning, and best practices.
- Translate business requirements into scalable agent-based solutions and AI roadmaps with product, business, and domain stakeholders.
- Drive technology strategy and innovation by tracking advances in multi-agent systems, cognitive architectures, and open-source AI frameworks.
Requirements
- 10+ years of overall professional experience, including 5+ years in Pharma and Biotech.
- Strong track record building domain-specific GenAI agents for Life Sciences use cases.
- Hands-on expertise with agentic and autonomous AI systems, multi-agent architectures, LLM orchestration, RAG pipelines, vector databases, and memory architecture.
- Proficiency in Python and experience with prompt engineering, tool integration, agent orchestration, and fine-tuning.
- Practical experience with commercial and open-source LLMs, including GPT-4, Claude, Gemini, and Mistral.
- Experience implementing adapters and RLHF where applicable.
- Experience designing, deploying, and operating cloud-native GenAI solutions on AWS, GCP, and Azure, including latency optimization, autoscaling, and cost control.
- Demonstrated leadership in architecture design, proof-of-concept development, and hands-on delivery in fast-paced environments.
- Experience with model cost profiling, real-time performance tuning, scalability strategies, and reliable agent behavior.
- Working knowledge of agent simulation, environment modeling, or reinforcement learning is a plus.
- Strong awareness of compliance, privacy, and safety requirements for enterprise GenAI deployments.