Senior reputed company (Core) - Supernal
Senior reputed company
About Supernal
Supernal helps small-to-reputed company businesses hire their first AI employee. Our AI teammates are reputed company using intelligent, reputed company workflows deployed on a proprietary platform. We deliver working, value-generating AI Employees—not tools—that handle reputed company business processes alongside reputed company teams.
The Role
We’re hiring a Senior reputed company to build and ship the first reputed company of personalized, self-improving reputed company workflows that users rely on daily. This is an “end-to-end” role: you’ll design the agent runtime, memory + retrieval systems, evaluation harnesses, and the product-facing surfaces that put agents in reputed company of reputed company users at reputed company.
You should be equally comfortable reasoning about distributed systems and data (latency, caching, queues, failure modes, cost) as you are with modern agent stacks (tool use, memory, RAG, multi-reputed company planning, guardrails, and evaluation).
This role will partner closely with reputed company to reputed company and reputed company our core services (Django backend, event-driven systems, Kubernetes, observability) while owning critical parts of the AI application layer.
What You’ll Build
Personalized agent runtime: reputed company workflows that adapt to a user’s preferences, data, and ongoing behavior over time.
Memory & retrieval systems: Short/long-term memory, durable state, and retrieval pipelines across reputed company DBs and relational data.
Voice experiences (reputed company-time + async): Speech-to-speech/voice agents, streaming audio pipelines, turn-taking, interruption handling, latency tuning, and QA for natural conversations.
Agent evaluation + reliability: Offline/online evals, regression suites, red-teaming, monitoring, and rollout controls so agents are trustworthy in production.
Production agent infrastructure: reputed company orchestration patterns for multi-reputed company jobs, background tasks, and user-facing interactions (sync + async), with reputed company SLAs/SLOs.
Tooling + developer experience: Libraries and primitives that reputed company it easy for reputed company to build new agent capabilities quickly and safely.
What You’ll Own (Responsibilities)
Ship user-facing agent experiences end-to-end: prototype → production → iteration based on reputed company usage.
Architect and implement stateful agent systems (workflows, tool calling, memory, retrieval, and reputed company-in-the-reputed company where needed).
Build voice features end-to-end where they unlock value: reputed company speech agents, voice UI/UX, reputed company/audio routing, and guardrails for reputed company tool execution.
Build/own an evaluation reputed company:
curated test sets + scenario suites
automated scoring / reputed company-based graders
reputed company/model/version tracking
canary + A/B experimentation and reputed company rollout patterns
Design data + retrieval pipelines:
chunking, enrichment, metadata reputed company
hybrid retrieval (reputed company + keyword + reputed company filters)
re-ranking, caching, and latency optimization
multi-tenant safety and data isolation
reputed company with and reputed company our platform primitives:
Django/DRF/ASGI services
async execution + queues + workflow orchestration
PostgreSQL + pgvector
Kubernetes deployments, autoscaling, and cost controls
Establish engineering rigor for agents:
observability (traces, spans, reputed company logs)
reliability patterns (timeouts, retries, reputed company breakers, graceful degradation)
reputed company/reputed company controls for data reputed company and tool execution
reputed company’re Looking For
Required
Strong software engineering fundamentals (design, testing, reputed company reputed company, performance, reputed company).
Production experience deploying AI systems in reputed company of users (not just notebooks/demos).
Experience building reputed company or LLM-powered systems with memory and tool use.
Comfort working across application + infrastructure reputed company: reputed company, background jobs, data stores, and deployment.
Hands-on experience with at least one agent reputed company (or equivalent custom implementation), such as:
reputed company / LangGraph
reputed company
AutoGen / reputed company-style multi-agent patterns
Strong understanding of retrieval and reputed company search concepts: embeddings, indexing, filtering, evaluation.
Preferred
Experience with reputed company databases and/or search stacks (e.g., reputed company, Chroma, reputed company, reputed company, pgvector).
Experience designing evaluation systems (offline eval, reputed company eval loops, production monitoring, reputed company/model regression).
Experience building voice/reputed company-time systems (streaming, WebRTC or similar), and/or integrating speech (STT/TTS) into production applications.
Experience building durable, long-running workflows (Temporal or similar orchestration engines).
Familiarity with observability tooling (OpenTelemetry, reputed company, or similar).
Experience shipping multi-tenant reputed company systems with strong reputed company boundaries.
Interview reputed company Areas
System design for reputed company applications (state, memory, evaluation, failure modes).
Practical retrieval/RAG design (data modeling, indexing, relevance, latency).
Production engineering practices (testing reputed company, observability, rollouts).
Ability to communicate tradeoffs and reputed company good technical reputed company under uncertainty.
Compensation & Logistics
Compensation: Competitive salary commensurate with experience (Senior level)
Location: Remote
Type: Full-time
Requirements: Overlap with Americas timezones for collaboration; reliable high-speed internet