Join our dynamic AI team as AI/ML Engineer focused on backend and AI system development. You will design, develop, and scale robust backend services and AI/ML pipelines using Python (3.11+), FastAPI. Your work will involve building advanced generative AI solutionssuch as retrieval-augmented generation (RAG) and agent-based workflowsleveraging large language models to solve real-world problems. Our projects span multiple verticals, including healthcare and management consulting, providing a unique opportunity to work on impactful, real-world challenges.
What you will be doing:
- Develop and maintain scalable backend APIs and services in Python (3.11+) using FastAPI
- Design and implement LLM-driven solutions, including prompt engineering and intelligent AI agent workflows
- Build and deploy Retrieval-Augmented Generation (RAG) pipelines using vector databases (Weaviate, Neo4j, Firestore)
- Leverage LangChain and LangGraph frameworks for orchestrating LLM interactions and knowledge graph tasks
- Integrate and manage data storage with Firebase Firestore or similar NoSQL databases on Google Cloud Platform (GCP)
- Process, clean, and analyze text data using NLP techniques to feed into AI pipelines
- Collaborate with cross-functional teams to translate requirements into robust AI features and ensure production readiness
- Create dashboards and developer tools (using JavaScript/TypeScript) for monitoring and analytics of AI systems
- Ensure code quality and follow best practices (testing, CI/CD) for reliable production deployments
You are a good match if you have:
- 3+ years of software engineering experience with a strong focus on Python (3.11+) and backend development
- Proficiency with FastAPI or similar Python web frameworks for building RESTful APIs
- Hands-on experience with large language models (LLMs) and Generative AI, including prompt engineering techniques
- Solid experience with LangChain and LangGraph (or equivalent orchestration frameworks)
- Proven track record in building RAG systems and deploying AI agents in production environments
- Proficient in using vector databases like Weaviate for semantic search and retrieval
- Strong NLP and text data processing skills (tokenization, embeddings, text analytics)
- Experience with Google Cloud Platform (GCP) services and Firebase Firestore (or other NoSQL databases)
- Basic proficiency in JavaScript/TypeScript for developing internal dashboards or front-end components
- Excellent communication, teamwork and problem-solving skills is must
You get extra points for:
- Experience with other cloud platforms (AWS, Azure) and cloud-native architectures
- Familiarity with containerization (Docker, Kubernetes) and CI/CD pipelines
- Experience with frontend frameworks (React, Vue) or visualization libraries for dashboards
Why join us
- You'll be a key early hire in a fast-moving, supportive, and experienced team.
- Reporting to the Head of Product Engineering, you'll have the autonomy to shape support, release, and onboarding processes as we scale.
- You'll work across the business and play a vital role in our customers success.
