Cynet Health is hiring a Senior AI Prompt Engineering Lead to architect, govern, and optimize complex LLM systems at the intersection of Agentic AI and Hiring Automation. This is a systems engineering role focused on designing cognitive architectures and building deterministic, scalable agents for our production environment.
What You'll Do
- Engineer production-grade prompt infrastructures for complex workflows including candidate evaluation, resume parsing, interview automation, and autonomous stakeholder communication.
- Deploy advanced prompting paradigms including Chain-of-Thought, Tree-of-Thought, Self-Consistency, and Instruction Hierarchies to ensure high-precision reasoning.
- Architect robust guardrails and instruction-following protocols to maintain system safety and prevent jailbreaks.
- Build and manage stateful, multi-agent workflows using LangGraph and LangChain.
- Design complex, multi-step decision trees that incorporate human-in-the-loop checkpoints, autonomous error recovery, and conditional branching.
- Optimize execution paths for latency and token cost without compromising system reliability.
- Architect Retrieval-Augmented Generation (RAG) pipelines that ensure high-fidelity context injection and minimize hallucinations.
- Manage integration with vector databases such as Pinecone, Weaviate, and Chroma, and implement advanced retrieval strategies.
- Define and implement automated evaluation frameworks (LLM-as-a-Judge) to conduct regression testing on prompts.
- Make strategic decisions regarding model routing and determine the viability of fine-tuning versus context-window optimization.
- Establish strict documentation standards for prompt versioning and reproducibility.
What We're Looking For
- Extensive hands-on experience with LangChain and LangGraph is non-negotiable.
- Mastery of prompt engineering for frontier models (GPT-4o, Claude 3.5 Sonnet, Gemini 1.5 Pro).
- A proven track record of deploying independent AI applications, specifically within HR Tech, Recruitment Automation, or Workflow Orchestration.
- Ability to conceptualize and build end-to-end AI systems, moving beyond isolated prompts to integrated cognitive architectures.
Nice to Have
- B.Tech/M.Tech from top-tier institutes is highly preferred.
- Experience operating in high-velocity, product-first environments where ownership and autonomy are paramount.
- Experience with OpenAI Assistants API and Function Calling.
- Familiarity with LLM observability platforms (LangSmith, Weights & Biases, PromptLayer).
- Expertise in adversarial prompting and security hardening for LLMs.
Technical Stack
- Frameworks: LangChain, LangGraph
- Models: GPT-4o, Claude 3.5 Sonnet, Gemini 1.5 Pro
- Vector Databases: Pinecone, Weaviate, Chroma
- APIs & Tools: OpenAI Assistants API, LangSmith, Weights & Biases, PromptLayer
Work Mode
This role offers a hybrid work mode and is open to remote candidates. A location in Dehradun is also an option.
