Machine Learning Engineer (Co-op / extended internship)
Engramme
With an account: save jobs, track applications, build tailored resumesAlready have an account? Log in
- Location
- San Francisco, CA
- Work style
- On-site
- Job type
- Internship
- Posted
- Oct 15
- 20 days ago
Build resumeBuild cover letterGenerate interview prepBuild resumeBuild cover letterGenerate interview prep
Career path
See where this role leads
Jigup maps the next three moves from a job like this one, with the titles and the skills each step asks for.
What you'll do
- You will build automated evaluation pipelines for memory retrieval, compression, and reconstruction while designing benchmarks for context retention and memory safety.
- Additionally, you will analyze model behavior, define quality metrics, and integrate evaluations directly into production systems.
What you need
- Candidates should have strong experience with Python and machine learning frameworks, along with a background in evaluation pipelines or model testing.
- A solid understanding of LLMs, retrieval systems, and the ability to reason from first principles are essential for this role.
- Education: a postgraduate degree
Key skills
PythonMachine LearningEvaluation PipelinesBenchmarkingLLMsEmbeddingsRetrieval SystemsModel TestingVector DatabasesSimilarity SearchInterpretabilityDistributed SystemsHigh-throughput PipelinesExperiment TrackingDebugging
Keywords for your resumePro
The words this employer's screening is likely to look for.
This job lists resume keywords
The terms this posting uses, pulled out so you can mirror them in your resume. Jigup Pro members see the list on the job board.
See full description on company page, apply now
Read the full posting here
This is a 6-month, in-person opportunity in San Francisco.
About Engramme
Engramme is a Frontier AI lab spun out of Harvard focusing on AI x Human Memory. Persistent memory is a fundamental open problem at the heart of AI. Our vision is to build models of human memory, and to endow humans with perfect and infinite memory.
Before starting Engramme, the founding team has produced and commercialized extensive research in machine learning and neuro-science inspired memory models:
Gabriel Kreiman (CEO & Co-founder): Professor of Neuroscience and AI, Harvard Medical School. Led key research on brain memory consolidation at Harvard University.
Spandan Madan (CTO & Co-founder): PhD in Computer Science from Harvard, designed AI models which were commercially deployed at Adobe, Fujitsu, and Meta.
What You’ll Do
Build automated eval pipelines for memory retrieval, compression, and reconstruction.
Design benchmarks for context retention, long-term consistency, and memory safety.
Analyze model behavior, surface failure modes, and define quality metrics.
Run large-scale experiments and maintain continuous evaluation systems.
Develop internal tools, dashboards, and workflows for fast debugging.
Integrate evals directly into production with backend + research teams.
What We’re Looking For
Strong Python + ML framework experience.
Background in eval pipelines, model testing, or benchmarking.
Understanding of LLMs, embeddings, or retrieval systems.
Ability to analyze failures, define metrics, and reason from first principles.
Comfortable moving fast and owning core architecture.
Nice to Have
Experience with vector DBs, similarity search, or interpretability.
Distributed systems or high-throughput pipeline experience.
Startup experience or ML tooling/open-source contributions.
Familiarity with monitoring/experiment-tracking tools.