Software Engineer, Conversational Products & Agent Workflows

Description

The company builds intelligent systems that can take action, learn from outcomes, and improve customer experiences over time, and it serves more than 167,000 customers while processing billions of consumer profiles, messages, interactions, and conversion signals.

You will join the Customer Agent team, the company's AI-native conversational platform, to build scalable backend systems and AI-driven product features that let agents fetch context, call tools, and act reliably for customers.

The role is mainly backend work, with some chance to contribute to user-facing features. You will own well-defined parts of larger systems, help shape technical decisions, and grow your skills in backend engineering, applied AI, and production reliability.

Responsibilities

• Build and improve reliable backend systems and APIs that support AI-driven customer experiences.
• Create production agent features covering tool use, context handling, retrieval, structured outputs, orchestration, and multi-step workflows.
• Help solve applied AI problems such as retrieval and RAG, grounding, reducing hallucinations, choosing models, and deciding between LLM-based, deterministic, or hybrid approaches.
• Build and run evaluations using representative datasets, automated and human review, regression tests, qualitative error analysis, and production signals.
• Improve reliability through guardrails, retries, fallbacks, observability, monitoring, and careful failure handling.
• Build asynchronous and distributed processing workflows that handle AI workloads at scale.
• Take part in an on-call rotation to diagnose and mitigate production incidents and learn from them.
• Work with external customers and cross-functional partners to understand their workflows, find pain points, and turn feedback into product changes.
• Track shipped features using quality metrics, system performance, and customer feedback to guide the next iteration.

Requirements

• You have 3+ years of professional software engineering experience, including building backend systems or distributed applications.
• You have hands-on experience building or contributing to generative AI or agentic AI applications, ideally used by real users or in production.
• You are proficient in Python and have worked with modern backend frameworks such as FastAPI or Django.
• You have experience with asynchronous or distributed task and event systems such as Celery, Kafka, SQS, RabbitMQ, or Redis.
• You have working knowledge of databases, data modeling, APIs, and persistence patterns used in production.
• You are comfortable in cloud environments and have used AWS, containers, Kubernetes, infrastructure automation, or CI/CD systems.
• You can weigh tradeoffs between quality, latency, cost, reliability, and implementation complexity, and you know when to ask for more technical context.
• You are at ease with ambiguity, can split large problems into smaller parts, and keep moving without every requirement spelled out.
• You have experience working directly with external customers to understand problems and improve products, or you are keen to start.
• You care about shipping useful, reliable products and want to sharpen your engineering judgment in a fast-changing technical field.
• Experience training, fine-tuning, distilling, or otherwise adapting machine learning or language models.
• Experience with reinforcement learning or feedback-driven optimization.
• Experience with evaluation infrastructure such as LLM-as-judge systems, evaluator calibration, benchmark datasets, or AI quality tooling.
• Experience running AI systems at meaningful production scale or optimizing inference cost, latency, or throughput.

Conditions

Base pay for US locations is $116,000 - $174,000 USD, reflecting the minimum and maximum target salary across all US locations, and the final offer depends on job-related skills, relevant experience, education or training, and work location.

Your recruiter can share more details on the salary range for your preferred location during the hiring process.

The role may require up to 10% travel for onboarding, client or partner work where relevant, team meetings, and industry events, and travel is arranged in advance.

The company is an equal opportunity employer that does not discriminate based on race, ethnicity, citizenship, national origin, color, religion, age, sex including pregnancy, gender identity, sexual orientation, disability, veteran or military status, marital status, criminal record, genetics, retaliation, sexual harassment, or any other legally protected characteristic.

Massachusetts law makes it unlawful to require or give a lie detector test as a condition of employment or continued employment.

Benefits

• Total compensation may include an annual cash bonus plan, equity, sign-on payments, and health, welfare, and wellbeing benefits based on eligibility.
• The company offers generous benefits and supports you from your first day, and it is open to accommodations as needed.
• The company encourages responsible use of AI, covering privacy, security, bias awareness, and human oversight.