Leads the team you would join
Leads the work day to day
Owns the opening
From your own Gmail and LinkedIn.
About the role
This is a full-time, remote MLOps role open to candidates based in India, focused on the infrastructure that runs production AI services. The work covers scaling model serving, building deployment and environment promotion pipelines, and creating internal tools so other teams can ship AI changes without infrastructure help. The team is part of American Heritage Lending, a private mortgage lender, and its AI systems already process live loans. The role suits engineers who have run containerized AI or ML services under real traffic and who prefer removing themselves from the critical path.
What you’ll do
- Re-architect AI service deployment into horizontally scalable, orchestrated infrastructure that handles traffic spikes.
- Own capacity planning, autoscaling and unit cost per unit of work for LLM-backed workloads.
- Build a promotion path across development, pre-production and production with reproducible environments.
- Put infrastructure, configuration and application logic under version control and review.
- Build CI/CD with rollback, staged rollout and an auditable change history.
- Create self-serve internal tooling that lets engineers and non-engineers define, test and promote AI workflow changes.
- Instrument the AI stack for latency, throughput, failure modes, cost and output quality, and set up alerting.
- Manage secrets, access control and environment isolation in a regulated lending environment.
What they’re looking for
- Hands-on ownership of containerized services in production, including rollouts, autoscaling, resource limits and rollback.
- Infrastructure as code with declarative, reproducible environments.
- CI/CD experience with automated testing, environment promotion and safe rollout.
- Strong Python skills, including reading, changing, profiling and fixing application code.
- Operational judgment across application, network and infrastructure layers.
- Ability to drive work end to end, including monitoring and follow-up after deployment.
Nice to have
- Experience operating LLM or ML workloads in production.
- Cloud deployment experience, with AWS preferred.
- Experience in fintech, lending, insurance or another regulated industry.
- Experience building internal developer platforms or self-serve tools.
- Comfort building a lightweight UI or internal tool when needed.
- Experience with multi-environment promotion pipelines where configuration and logic move with code.
- Familiarity with agent orchestration frameworks.
- Observability for non-deterministic systems, including tracing and quality monitoring.
- Inference optimization such as batching, caching and cost reduction.
- Exposure to workflow automation or low-code builder tools.
What’s on offer
- Competitive compensation.
- Unlimited paid time off.
- Remote-first work with flexible hours.
- A professional development budget of $2,000 per year.
- A home office setup stipend.
Skills
Questions about this role
Is this MLOps Engineer role remote?
Yes. The role is remote and listed for candidates in India.
What skills does this role require?
It asks for production ownership of containerized services, infrastructure as code, CI/CD depth and strong Python.
Are there benefits?
The posting lists unlimited PTO, flexible hours, a $2,000 yearly development budget and a home office stipend.