Senior Engineer-ai Inference

Bank of America Merrill Lynch

In-office with flexible attendance based on role-specific considerations.
8+ years relevant experience
Python development on linux
Vllm or triton inference server
Bank of America Merrill Lynch is seeking a Senior Engineer for AI Inference to join their innovative team focused on developing a Gen AI platform. The role involves designing and delivering complex features for AI initiatives while fostering an inclusive workplace culture

Job Summary

  • This role focuses on defining and leading the engineering approach to deliver complex features for a next-generation Gen AI platform.
  • The position requires hands-on experience deploying and tuning models using vLLM or Triton Inference Server to ensure high throughput and scalability.
  • Candidates must possess strong analytical skills to solve problems, challenge conventions, and manage multiple priorities across global teams.

Matching Summary

Match Score: 85

Bank of America Merrill Lynch is seeking a Senior Engineer for AI Inference to join their innovative team focused on developing a Gen AI platform. The role involves designing and delivering complex features for AI initiatives while fostering an inclusive workplace culture.

Skills & Requirements

Must-have

  • 8+ years relevant experience
  • Python development on Linux
  • vLLM or Triton Inference Server
  • Vector Store platforms (Redis, FAISS)
  • Model Ops and MLOps design
  • CI/CD pipeline implementation
  • RAG framework development

Nice-to-have

  • Experience with open-source models
  • Strong stakeholder management skills
  • Mentoring and coaching team members
  • Knowledge of MCP modules
  • Policy as Code implementation
  • Cross-functional collaboration
  • Test Driven Development practices

Key Requirements

  • Minimum 8 years of relevant experience
  • Hands-on Python development on Linux
  • Experience with Model Ops and AI/ML delivery
  • Proficiency in vector store platforms like Redis and FAISS
  • Expertise in model evaluation and monitoring frameworks

Work Rights

Not specified

Tailored Resume

Cover Letter