Capital Numbers
Website:
capitalnumbers.com
Job details:
We are looking for a hands-on Lead AI Engineer who can design, build, and deliver production-grade AI and GenAI solutions.
The ideal candidate will combine strong software engineering fundamentals with practical experience in Generative AI, LLMs, RAG, AI agents, machine learning, and cloud-based AI applications.
As a Lead AI Engineer, you will work closely with solution architects, engineering leaders, product teams, and clients to translate business requirements into scalable AI solutions. You will lead technical implementation, build PoCs, establish engineering standards, mentor developers, and remain hands-on with coding and architecture.
Key Responsibilities
- Design and develop production-grade AI, GenAI, and machine learning applications.
- Lead the technical implementation of LLM-powered applications, AI agents, RAG systems, chatbots, automation solutions, and AI integrations.
- Build rapid PoCs and convert successful prototypes into scalable production solutions.
- Design AI application architecture covering models, APIs, databases, vector stores, integrations, security, and deployment.
- Develop backend services and APIs using Python and frameworks such as FastAPI.
- Integrate models and AI services from providers such as OpenAI, Azure OpenAI, Anthropic, Gemini, or comparable platforms.
- Design and implement RAG pipelines using embeddings, semantic search, vector databases, and retrieval strategies.
- Build agentic workflows involving tool calling, function calling, workflow orchestration, and multi-step reasoning.
- Implement LLM evaluation, prompt engineering, guardrails, observability, and hallucination-reduction mechanisms.
- Integrate AI applications with enterprise systems, databases, REST APIs, webhooks, and third-party platforms.
- Deploy and operate AI applications across AWS, Azure, or Google Cloud.
- Conduct code reviews and establish coding, testing, documentation, security, and engineering standards.
- Troubleshoot production issues and optimize application performance, latency, reliability, and cloud costs.
- Mentor AI/ML engineers and developers and provide technical direction to the team.
- Collaborate with product managers, architects, and stakeholders to translate business requirements into technical solutions.
- Participate in technical discussions, solution design, estimation, and client-facing engagements when required.
Required Technical Skills
- Strong hands-on programming experience in Python.
- Strong experience with FastAPI or comparable Python backend frameworks.
- Working knowledge of Node.js and/or TypeScript.
- Strong understanding of Generative AI, LLMs, prompt engineering, RAG, embeddings, semantic search, and vector databases.
- Hands-on experience building AI agents and agentic workflows using tool/function calling and workflow orchestration.
- Experience with frameworks/tools such as LangChain, LlamaIndex, LangGraph, or comparable technologies.
- Experience integrating OpenAI, Azure OpenAI, Anthropic, Gemini, or equivalent LLM providers.
- Strong understanding of REST APIs, authentication, webhooks, databases, and third-party integrations.
- Experience with vector databases such as Pinecone, Qdrant, Weaviate, Milvus, FAISS, pgvector, or equivalent.
- Experience deploying AI applications on AWS, Azure, or GCP.
- Working knowledge of Docker, CI/CD, monitoring, logging, secrets management, and production support.
- Understanding of LLM evaluation, guardrails, observability, prompt management, latency optimization, and cost optimization.
- Understanding of secure AI architecture, including PII protection, access control, data privacy, and tenant isolation.
- Good understanding of applied ML concepts such as predictive analytics, classification, recommendation systems, NLP, OCR, computer vision, or voice AI.
- Ability to build lightweight UI/demo applications for AI solutions is an advantage.
Required Professional Experience
- 8–10+ years of software engineering experience.
- 4+ years of hands-on experience delivering AI/ML solutions.
- Strong recent experience building and deploying GenAI/LLM applications.
- Proven experience taking AI solutions from PoC/prototype to production.
- Experience leading the technical implementation of AI projects.
- Experience mentoring and guiding AI/ML or software engineering teams.
- Strong experience in software architecture, API development, integrations, and cloud deployment.
- Experience working in an IT services, consulting, product engineering, or technology environment.
- Strong problem-solving and debugging skills.
- Ability to work hands-on while providing technical leadership to the team.
Preferred Experience
- Experience with AI agents, multi-agent systems, or agentic AI architectures.
- Experience building reusable AI accelerators, frameworks, or internal platforms.
- Experience with LLMOps/MLOps and production AI monitoring.
- Experience with AI applications across multiple business domains.
- Experience working with international clients.
- Exposure to pre-sales, technical discovery, estimation, or solutioning.
- Experience with enterprise AI integrations and workflow automation.
- Knowledge of fine-tuning, model evaluation, or model optimization.
Click on Apply to know more.
