Research Engineer — Privacy & Security

Meramia Technologies LTD; Time; On-site; NOK 900,000 - 1,100,000; Full time

Job summary

Meramia Technologies LTD seeks a privacy-focused ML engineer to turn research成果 into production code for privacy guarantees inside the training and inference stacks.

You will prototype DP, secure aggregation, and federated learning; build evaluation suites; work with cross-functional teams to embed regulations as guardrails in code and trade privacy for utility with measurable guarantees.

Qualifications

• Experience turning privacy research into production code.
• Ability to explain a mathematical privacy guarantee to technical and non-technical stakeholders.
• Track record of building evaluation suites for ML privacy and security.

Responsibilities

• Prototype and land privacy-enhancing algorithms on training and inference stacks.
• Red-team models for membership inference, inversion, and training-data memorisation; document failures.
• Build evaluation suites and diagnostic libraries for ML engineers.
• Collaborate with research, platform, security, legal, and product to embed guardrails into code.
• Investigate privacy-utility trade-offs across capability, latency and cost.

Skills

DP/Privacy algorithms

PyTorch or JAX

Research-grade Python

Differential privacy DP-SGD

Security testing / leakage

Explainability to engineers & policy

Tools

DP-SGD

Federated learning

Security testing tools

Job description

The work.

Meramia's knowledge work already lives inside boundaries the client is held to. This role makes those boundaries measurable: privacy-enhancing techniques on the training and inference path, red-team tests for leakage, and tools the rest of the lab can run without a paper as a crutch.

You will turn a result from the literature into code that ships, and you will say when a privacy guarantee is real and when it is a slide.

01 What you will do

• Prototype and land privacy-enhancing algorithms — differential privacy, secure aggregation, federated learning — on the training and inference stacks we actually run.
• Red-team the models for membership inference, inversion, and training-data memorisation. Write the failure down before someone else finds it.
• Build the evaluation suites and diagnostic libraries ML engineers can use across a model's life, not a one-off notebook.
• Sit with research, platform, security, legal and product so a regulation or a security principle becomes a guardrail in code.
• Investigate the privacy-utility trade: capability, latency and cost against a guarantee you can state.

02 What you bring

• PyTorch or JAX, and research-grade Python you will test rather than demo.
• Differential privacy (including DP-SGD), secure multiparty computation, or federated learning — implemented, not only cited.
• The attack surface: extraction, membership inference, poisoning — and how you measured it.
• A paper you can turn into a well-tested module without losing the claim that made the paper worth reading.
• The ability to explain a mathematical privacy guarantee to an engineer and to a policy lead in the same week.

03 Useful, not required

• Peer-reviewed work or open-source in privacy, security, cryptography or machine learning — NeurIPS, ICLR, USENIX Security, IEEE S&P, or the equivalent venue.
• PETs on a distributed train or a high-throughput inference path, not only on a single node.

04 What to send

• A CV and the two profile links the form asks for.
• One privacy or leakage result you implemented — the threat, the metric, and the trade you accepted.

05 The first quarter

• Audit the privacy evaluations and training workflows already in use.
• Ship one automated evaluation or differential-privacy module into the internal ML path.
• Write the privacy-utility result for the architectures we serve, with a deployable recommendation.