AI Engineer
About the Role
Kenpath Technologies is a forward-thinking company building cutting-edge AI solutions across multiple domains. As an AI Engineer, you'll design and implement LLM-powered systems that are scalable, efficient, and reliable.
What you'll do
- Develop LLM-powered features like RAG pipelines, summarization, structured data extraction, and conversational AI workflows.
- Work with various model providers (OpenAI, Anthropic, Google Gemini, etc.) to select the best-fit models for each task.
- Build and optimize retrieval systems using hybrid search, vector stores, and re-ranking techniques.
- Design evaluation frameworks to measure and iterate on model performance and quality metrics.
- Monitor and optimize AI API costs, token usage, and latency in production systems.
- Write clean, production-grade Python code using frameworks like FastAPI and Pydantic AI.
- Stay updated on AI advancements and recommend practical, tested solutions to the team.
This is a unique opportunity to work on impactful AI-driven solutions, collaborate with a dedicated team, and stay at the forefront of the rapidly evolving AI landscape.
Requirements
Core
2–5 years of software engineering experience, including 1–2 years of hands-on LLM/GenAI work.
Proficiency in Python, including async programming and API development.
Experience integrating LLM APIs for tasks like prompting, structured outputs, and streaming.
Knowledge of RAG systems, including embeddings, vector databases, and retrieval strategies.
Understanding of token economics, context management, and cost-aware design.
Working knowledge of SQL (PostgreSQL preferred) and cloud deployment (AWS preferred).
Evidence-driven mindset with strong experimentation and evaluation skills.
Clear and effective written communication skills for documenting architectures and trade-offs.
Nice to have
Experience with speech-to-text pipelines, OCR, or multilingual NLP (Indian languages a plus).
Familiarity with agent frameworks like Pydantic AI or LangGraph.
Background in fine-tuning, model evaluation tools, or LLM observability.
Experience in agritech, govtech, or social-sector AI applications.
Open-source contributions or published technical writing.