Agentic AI Engineer

Agentic AI Engineer | 8 -10 Years | 5+ years in Pharma and Biotech | US | Remote, US Citizen or Green card holder willing to work on 1099 | Immediate joiners
We’re looking for an AI Architect who can do more than design PowerPoint architectures — someone who can architect, build, deploy and scale production-grade Agentic AI solutions.
This is a hands-on role for someone who has worked with LLMs, multi-agent systems, RAG and AI orchestration and understands what it takes to move an AI solution from business problem → architecture → PoC → production → scale.
What you’ll be working on
🔹 Design and implement Agentic AI and multi-agent architectures using frameworks such as LangGraph, LangChain, CrewAI, AutoGen and similar technologies.
🔹 Apply patterns such as planner–solver, hierarchical agents, autonomous teams and goal decomposition to solve complex enterprise problems.
🔹 Define end-to-end AI architecture covering LLM/model selection, orchestration, memory, tools, security, observability and deployment.
🔹 Build reusable agent tooling, APIs, memory and integration layers that enable scalable enterprise AI applications.
🔹 Lead the development and production deployment of AI assistants, copilots, workflow automation and decision-support systems.
🔹 Work with LLMs and multimodal models including OpenAI, Claude, Gemini, Mistral, LLaMA and others, along with RAG and vector databases.
🔹 Design for the realities of production AI: latency, scalability, reliability, token economics, security, privacy, hallucination and responsible AI.
🔹 Establish GenAIOps / LLMOps practices covering evaluation, monitoring, logging, feedback loops and continuous improvement.
🔹 Work directly with product, business and domain stakeholders to translate business problems into scalable AI solutions and transformation roadmaps.
Must have skillsets:
· 10 years of overall experience, including 5+ years in Pharma and Biotech, with a strong track record in building domain-specific GenAI agents for Life Sciences use cases.
· Hands-on expertise in agentic and autonomous AI systems, including multi-agent architectures and frameworks such as LangChain, LangGraph, CrewAI, AutoGen, Haystack, AutoGPT, BabyAGI, CAMEL, and MetaGPT.
· Strong Python proficiency with deep experience in prompt engineering, tool integration, agent orchestration, RAG pipelines, vector databases, and memory architecture.
· Practical experience working with commercial and open-source LLMs (GPT-4, Claude, Gemini, Mistral) and implementing fine-tuning, adapters, and RLHF where applicable.
· Proven ability to design, deploy, and operate cloud-native GenAI solutions on AWS, GCP, and Azure, with focus on 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, and scalability strategies, ensuring reliable and efficient agent behaviour
· Working knowledge of agent simulation, environment modelling, or reinforcement learning is a plus, along with strong awareness of compliance, privacy, and safety requirements for enterprise GenAI deployments.

Work arrangement
No