AI Engineer

Role Purpose 

As an AI Engineer at Prevalent AI, you will independently design, build, optimize, and deploy production-grade Generative AI systems across our Exposure Management and Data Fabric platforms. You will own end-to-end AI components such as RAG pipelines, multi-agent workflows, LLM-backed APIs, guardrail-enforced inference flows, and cloud-native AI integrations, while collaborating closely with platform, backend, and product teams. 

This role is suited for engineers with hands-on, real-world experience building and operating GenAI systems in production, who can take ownership of design decisions, performance tuning, and reliability of AI-driven features. 

Key Accountabilities 

• Design, build, and own production-ready GenAI systems, including RAG pipelines, embedding workflows, vector search architectures, tool-using agents, and LLM-integrated microservices. 

• Create and manage MCP servers and associated tools, integrating and orchestrating them via AI agents 

• Develop and maintain Fast API-based AI services integrated with LLMs, vector databases, cloud inference endpoints, and orchestration layers. 

• Architect and implement agentic AI pipelines using frameworks such as Lang Chain, Lang Graph, ADK, Crew AI, or other relevant agent-based frameworks for multi-step reasoning, tool orchestration, autonomous agents, and structured LLM workflows. 

• Integrate and operate cloud-based AI services using Google ADK (Gemini / Vertex AI), AWS Bedrock, or Azure OpenAI, including model selection, endpoint configuration, and cost-aware inference. 

• Apply advanced prompt engineering strategies (structured prompting, React, CoT, few-shot, tool-calling) and systematically reduce hallucinations and failure modes. 

• Implement and contribute to LLM fine-tuning workflows (LoRa, QLoRA, PEFT), including dataset preparation, training, evaluation, and deployment considerations. 

• Design and enforce AI guardrails using frameworks such as NeMo Guardrails or Guardrails AI to ensure policy-compliant, safe, and explainable outputs. 

• Lead model evaluation and optimization, focusing on latency, accuracy, robustness, hallucination mitigation, and cost efficiency. 

• Own testing and deployment of AI services, including unit tests, integration tests, CI/CD pipelines, and environment-specific configurations (cloud/on-prem). 

• Produce and maintain high-quality technical documentation covering prompts, workflows, vector schemas, architectural decisions, and API contracts. 

• Collaborate with cross-functional teams to translate product requirements into scalable, reliable AI solutions and mentor junior engineers when needed. 

Skills & Experience 

Must have skills: 

• Strong hands-on experience with LangChain and LangGraph for building and operating complex LLM workflows and agentic systems. 

• Proven experience designing and deploying Retrieval-Augmented Generation (RAG) pipelines using embedding models and vector databases such as FAISS, Pinecone, Chroma, or equivalent. 

• Solid backend engineering experience with FastAPI, including async APIs, dependency injection, authentication, and service observability. 

• Practical experience with LLM fine-tuning approaches (LoRA, QLoRA, PEFT) and understanding of when to fine-tune vs prompt vs retrieve. 

• Advanced understanding of prompt engineering, including CoT, React, tool calling, schema-based prompting, and prompt versioning strategies. 

• Experience implementing AI safety and guardrails, including output validation, policy enforcement, and prompt injection mitigation. 

• Hands-on exposure to cloud AI platforms such as Google ADK / Vertex AI, AWS Bedrock, or Azure OpenAI in production environments. 

• Strong Python skills with experience using Transformers, Hugging Face, embedding models, and inference optimization techniques. 

Good to have skills: 

• Exposure to FastMCP or similar frameworks is an added advantage. 

• Good understanding of LLM evaluation metrics, hallucination control strategies, and real-world failure patterns.