AI Engineer – AI Agent Development

About the Role

We are seeking a highly motivated AI Engineer with 1–3 years of hands-on experience building and deploying AI Agents using Google AI Agent Platform (Vertex AI) or AWS Bedrock. This role is ideal for an engineer passionate about building applied AI solutions—including intelligent agents, automation flows, RAG pipelines, and enterprise-grade AI micro-services.

You will be part of a fast-paced product and innovation team responsible for designing, developing, and scaling AI Agents that automate real business workflows across life sciences, healthcare, consumer products, and enterprise systems.

Key Responsibilities
AI Agent Development

• Design, develop, and deploy production-grade AI Agents using Google Vertex AI Agents or AWS Bedrock Agents.
• Build end-to-end AI agent workflows including LLM orchestration, tool invocation, guardrails, and monitoring.
• Implement RAG (Retrieval-Augmented Generation) pipelines for dynamic and context-aware agent responses.
• Integrate AI Agents with enterprise applications, APIs, data sources, and external tools.

AI Engineering & Architecture

• Build scalable backend components using Python, FastAPI/Flask, and microservice patterns.
• Develop and integrate RESTful APIs and secure agent–system interactions.
• Implement model evaluation, prompt engineering, embeddings, hallucination controls, and response validation.
• Work across Vector Databases (Pinecone, ChromaDB, Milvus, Weaviate) and RDBMS (PostgreSQL, MySQL).

LLM & Platform Engineering

• Fine-tune, optimize, and evaluate LLMs for accuracy, safety, and performance.
• Leverage Google Vertex AI (Model Garden, Vector Search, Agents, Workbench) or AWS Bedrock (Agents, Guardrails, Knowledge Bases).
• Collaborate with product teams to understand use cases and convert them into AI agent workflows.

Quality, Monitoring & MLOps

• Deploy AI agents to production using CI/CD, containerization (Docker), and cloud deployment best practices.
• Implement logging, monitoring, evaluation pipelines, and feedback loops to ensure reliability.
• Apply security, privacy, and responsible AI principles (PII handling, content filters, guardrails).

Required Skills & Experience

• 1 to 3 years of hands-on AI Agent development experience.
• Successfully developed and deployed at least one AI Agent into production.
• Hands-on experience with Google Vertex AI, AWS Bedrock, LLMs, and RAG pipelines.
• Strong experience with Vector Databases (Pinecone, Weaviate, Chroma, Milvus) and RDBMS.
• Proficiency in Python for backend and AI development.
• Experience with API development (FastAPI, Flask, API Gateway, Cloud Functions, Lambda).
• Familiarity with prompt engineering, embeddings, and LLM evaluation.
• Strong understanding of cloud platforms (Google Cloud or AWS).
• Experience handling unstructured data (documents, PDFs, images, JSON, logs).

Nice-to-Have Skills

• Experience with Google AI Studio, Vertex AI Search & Conversation, or Vertex AI Extensions.
• Experience with LangChain, LlamaIndex, CrewAI, AutoGen, or similar AI orchestration frameworks.
• Exposure to MLOps tools (Vertex Pipelines, AWS SageMaker, MLflow).
• Knowledge of GenAI safety, guardrails, PII redaction, and content filters.
• Experience building multi-agent systems.
• Understanding of event-driven architectures (Pub/Sub, SQS, EventBridge).
• Familiarity with frontend frameworks (React) to support simple agent UI prototypes.

Soft Skills & Work Style

• Ability to work in a fast-paced, startup-like environment.
• Strong problem-solving mindset with ownership of end-to-end delivery.
• Excellent communication and documentation skills.
• Ability to collaborate cross-functionally with product managers, designers, and engineering leaders.
• Passion for innovation, experimentation, and pushing the boundaries of applied AI.

Why Join Us ?

• Work on cutting-edge applied AI technologies.
• Opportunity to build real-world AI agents used by global enterprises.
• Fast-paced environment with room for rapid growth.
• Be part of an AI Innovation Lab shaping the future of life sciences and enterprise AI.

---