Generative AI Engineer

We’re looking for a Generative AI Engineer who knows how to turn models into real-world systems—not just by fine-tuning, but by mastering prompting, template-driven workflows, and agentic AI architectures. You’ll build intelligent agents, design predictable prompt frameworks, and use tools like LangGraph to orchestrate complex, multi-step AI behaviors inside production-grade products.

Responsibilities

Prompting & Template Engineering

• Design, optimize, and maintain prompt templates, reusable prompt frameworks, and evaluation pipelines.

• Implement structured prompting patterns (chain-of-thought, RAG prompting, tool-calling prompts, guardrails, etc.).

• Build automated systems for prompt testing, versioning, and performance tracking.

Agentic AI & LangGraph Development

• Build agent workflows using LangGraph (or similar frameworks) for stateful, multi-step reasoning.

• Add and manage tool integrations (APIs, vector DBs, custom functions) into agent pipelines.

• Ensure deterministic, safe, and traceable agent execution for real-world applications.

Data & Model Interaction

• Work with embeddings, vector DBs, retrieval pipelines, and dataset preprocessing.

• Evaluate and refine model outputs through prompt adjustments rather than brute-force fine-tuning.

• Collaborate on model selection, system design, and performance optimization.

Deployment & Integration

• Work with engineering teams to embed agentic AI into web apps, internal tools, and customer-facing solutions.

• Support the creation of reusable AI modules, internal APIs, and automation assistants.

Research & Continuous Improvement

• Experiment with new agent frameworks, prompting techniques, and orchestration tools.

• Stay current with frontier models, agent systems, and best practices.

Requirements (1–2 Years Experience in AI and Overall experience of at least 2 years)

• Strong understanding of prompt engineering, structured prompting, and model behavior.

• Hands-on experience with LangGraph, LangChain, or agentic AI frameworks.

• Good Python skills and familiarity with API integrations.

• Practical experience with vector databases (Pinecone, Weaviate, Chroma, Supabase, Qdrant, etc.).

• Ability to design RAG workflows, tool-calling prompts, and agent reasoning flows.

• Familiarity with LLM APIs (OpenAI, Anthropic, Azure OpenAI, etc.).

• Solid grasp of evaluation methods for LLM outputs and prompt performance.

• Understanding of basic ML concepts (tokenization, embeddings, model inference, evaluation).

Nice to Have

• Experience building production-grade AI assistants or multi-agent systems.

• Exposure to Autonomous Agents, LangGraph dynamic state machines, or tool-based agent routing.

• Knowledge of lightweight fine-tuning (LoRA, QLoRA, adapters) and dataset generation.

• Understanding of orchestration tools (n8n, make).

• Experience with cloud platforms (Azure, AWS, GCP).