AI Architect / Tech Lead (mahjong game)

Neurons Lab; Roma; In loco; EUR 95.000 - 150.000; Part-time

Descrizione del lavoro

Neurons Lab is seeking a Hands-on Tech Lead for an AI companion in an online mahjong game. You will design and build the mahjong-playing algorithm with RL, imitation learning, or search-based methods, and integrate an LLM reasoning layer.

You’ll own the end-to-end architecture, ensure a 2-second per-move latency budget, define data interfaces, and collaborate with client engineers and CTO to explain trade-offs.

Competenze

• Hands-on ML/AI engineering at production scale.
• Shipped an AI system inside a live product with hard latency limits.
• 6+ years hands-on ML/AI engineering, with real game AI or sequential decision-making work (RL / MCTS / self-play).

Mansioni

• Design and build the mahjong-playing algorithm: choose and defend the approach (imitation learning on hand histories, RL / self-play, search with MCTS, or a hybrid).
• Own the technical architecture end to end: game model + LLM reasoning layer, valid-action mask, win detection, and API contract with the client’s game bridge.
• Hit the 2-second response budget: design and measure the inference path, batching, and caching; keep a latency buffer for the client-facing number.
• Define data and event names from the client (hand histories, event streams); build training and calibration pipelines.
• Build and run the evaluation harness: measure play strength against reference points and validate explanations.
• Stand up LLM observability with Langfuse (async logging, N+1 batching).
• Take over context from leadership and lead the sprint with the AI engineer; collaborate with client CTO and engineers.
• Watch licensing, engine-bridge capabilities, and multi-rule-set scope risks.

Conoscenze

ML/AI engineering

Production systems

RL / MCTS / self-play

Python for ML

Low-latency inference

LLM integration

Cloud AWS

Technical leadership

Strumenti

Langfuse

Descrizione del lavoro

About The Project (description, Duration, Stage)

Hands-on Tech Lead for an AI Companion in an online mahjong game. The client is a social gaming company (web3 element) that scales its product and team. We deliver the AI side of their game as their embedded AI partner. The AI Companion plays mahjong at a strong level and explains its moves. The core of the role is to build the mahjong-playing algorithm: a dedicated decision-making model (RL, imitation learning, or search-based — trained on the client's hand-history data) with an LLM reasoning layer on top. Key design constraints: a valid-action contract with the game engine (the bridge supplies legal moves), win detection, and a 2-second response budget per move. Explanations run async. Support for more than one rule set (riichi and regional variants) is on the roadmap.

Duration: 3 months, 0.5 FTE.

What You’ll Actually Do (example Tasks)

• Design and build the mahjong-playing algorithm: choose and defend the approach (imitation learning on hand histories, RL / self-play, search with MCTS, or a hybrid), then train, evaluate, and ship it.
• Own the technical architecture end to end: game model + LLM reasoning layer, valid-action mask, win detection, and the API contract with the client's game bridge.
• Hit the 2-second response budget: design and measure the inference path, batching, and caching; keep a latency buffer for the client-facing number.
• Define what data and event names we need from the client (hand histories, event streams); build the training and calibration pipeline on that data.
• Build and run the evaluation harness: measure play strength against the client's reference points, and validate explanation quality.
• Stand up LLM observability with Langfuse (async logging, N+1 batch) as an early sprint quick win.
• Take over context from Vlad Borysenko (0.15–0.2 FTE supervision during ramp-up) and lead the sprint work with the AI Engineer; work with the client's Product Owner in a scrum process.
• Front the client's CTO and engineers on technical decisions; explain trade-offs in plain language and in depth when asked.
• Watch the risks the account team flagged: licensing on new training data, engine-bridge capabilities, and multi-rule-set scope.

Skills (hands-on first)

• Game AI / sequential decision-making: hands-on RL, imitation learning, or search-based agents (MCTS, self-play) — ideally for imperfect-information games (mahjong, poker, card games)
• Expert Python for ML systems; strong software engineering (APIs, testing, CI)
• Model training on gameplay data end to end: data → training → evaluation → serving
• LLM application engineering: reasoning layers, prompt and context design, structured outputs, guardrails
• Low-latency inference: profiling, batching, caching, model-size trade-offs against a hard time budget
• LLM observability and evaluation (Langfuse or similar)
• AWS deployment for ML workloads
• Technical leadership of a small pod; clear written and spoken communication with client engineers and executives

Knowledge

• Game theory for imperfect-information games; evaluation of play strength (win rates, Elo-style ratings, baseline agents)
• Game-engine integration patterns (event streams, action masks, state bridges)
• Web3 / gaming product context — plus, not required
• AWS Well-Architected for ML workloads

Experience

Key characteristics (ideally 4/4):

• Hands-on ML/AI engineering at production scale
• Shipped an AI system inside a live product with hard latency limits
• Cloud hyperscaler experience (AWS preferred)
• Technology consulting / client-facing delivery background

Role-specific characteristics:

• 6+ years hands‑on ML/AI engineering, with real game AI or sequential decision-making work (RL / MCTS / self-play — not only LLM apps)
• Trained models on user or gameplay data end-to-end (data → training → evaluation → serving)
• Led small delivery teams while still coding personally
• Comfortable owning an architecture in front of a technical client CTO

Questions for Applicants

• Imperfect information: mahjong hides most tiles from each player. How does hidden information change your algorithm choice compared to a perfect-information game like chess?
• Latency budget: tell us about a system you shipped with a hard response-time limit. How did you design, measure, and defend the budget?
• LLM + model hybrid: how would you combine a trained game model with an LLM explanation layer so the explanation never contradicts the move?
• Hands‑on + lead: how do you balance personally coding the hard parts with leading an engineer and fronting the client?